O
GPT-5.6
OpenAIgpt-5.6Frontier GPT reasoningContext372k
Max out128k
Input / 1M$1.5cached $0.15
Output / 1M$12
ChatReasoning / thinkingFunction calling
Model catalog
OpenAI compatiblexpersona / modelsLive catalogUse genuine GPT, Claude, Gemini, and Xpersona models through one API key, one OpenAI-compatible endpoint, and one place to track usage. Switch models per request without changing your integration.
New arrivals
Model catalog
O
GPT-5.6 Sol
OpenAIgpt-5.6-solAgentic GPT coding and deep workContext372k
Max out128k
Input / 1M$1.5cached $0.15
Output / 1M$12
ChatReasoning / thinkingFunction calling
O
GPT-5.6 Terra
OpenAIgpt-5.6-terraBalanced GPT intelligence and efficiencyContext372k
Max out128k
Input / 1M$1.5cached $0.15
Output / 1M$2
ChatReasoning / thinkingFunction calling
O
GPT-5.5
OpenAIgpt-5.5Long-context GPT reasoningContext1050k
Max out128k
Input / 1M$1.5cached $0.15
Output / 1M$12
ChatReasoning / thinkingFunction calling
O
GPT-5.4
OpenAIgpt-5.4Reliable general-purpose GPT reasoningContext1050k
Max out128k
Input / 1M$0.75cached $0.075
Output / 1M$6
ChatReasoning / thinkingFunction calling
O
GPT-5.4 Mini
OpenAIgpt-5.4-miniFast, economical GPT reasoningContext272k
Max out128k
Input / 1M$0.375cached $0.037
Output / 1M$4
ChatReasoning / thinkingFunction calling
A
Claude Opus 4.8
OpenAIclaude-opus-4-8Premium Claude analysis and codingContext200k
Max out128k
Input / 1M$1.5cached $0.15
Output / 1M$9.25
ChatFunction calling
A
Claude Sonnet 4.6
OpenAIclaude-sonnet-4-6Balanced Claude intelligenceContext200k
Max out128k
Input / 1M$0.9cached $0.09
Output / 1M$5.55
ChatFunction calling
A
Claude Haiku 4.5
OpenAIclaude-haiku-4-5Fast Claude responsesContext200k
Max out128k
Input / 1M$0.6cached $0.06
Output / 1M$3.7
ChatFunction calling
G
Gemini 3.5 Flash
OpenAIgemini-3.5-flashFast multimodal Gemini reasoningContext1M
Max out128k
Input / 1M$1.55cached $0.155
Output / 1M$12.2
ChatReasoning / thinkingFunction calling
A
Claude Opus Latest
OpenAIclaude-opus-latestStable alias for genuine Claude Opus 4.8Context200k
Max out128k
Input / 1M$1.5cached $0.15
Output / 1M$9.25
ChatFunction callingImage inputPrompt cachingStructured outputs
A
Claude Sonnet Latest
OpenAIclaude-sonnet-latestStable alias for genuine Claude Sonnet 4.6Context200k
Max out128k
Input / 1M$0.9cached $0.09
Output / 1M$5.55
ChatFunction callingImage inputPrompt cachingStructured outputs
O
OpenAI GPT Latest
OpenAIopenai-gpt-latestStable alias for genuine GPT-5.6Context372k
Max out128k
Input / 1M$1.5cached $0.15
Output / 1M$12
ChatReasoning / thinkingFunction callingPrompt cachingStructured outputs
A
Claude Fable 5
OpenAIclaude-fable-5Genuine Claude Fable 5 through XpersonaContext1M
Max out128k
Input / 1M$3cached $0.3
Output / 1M$18.5
ChatFunction callingImage inputPrompt cachingStructured outputs
X
Xpersona A_BETTER_YOU
OpenAIxpersona-a-better-youExtra-high reasoning for ambitious OpenCode workContext1M
Max out128k
Input / 1M$3cached $0.3
Output / 1M$18
ChatReasoning / thinkingFunction callingImage inputPrompt caching
X
Xpersona Frieren 1
OpenAIxpersona-frieren-coderCoding Agent LLM for Windows/MacOSContext1M
Max out384k
Input / 1M$1.5cached $0.15
Output / 1M$6
ChatReasoning / thinkingFunction callingImage inputStructured outputs
Code examples
from openai import OpenAI
client = OpenAI(
base_url="https://www.xpersona.co/v1",
api_key="YOUR_XPERSONA_API_KEY",
)
response = client.chat.completions.create(
model="gpt-5.6-sol",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)Uptime & status
Inference API
View status Live operational history and incident reporting
Public model endpoint
Open endpoint Machine-readable model discovery for connected clients
One key. Every model.
Start with a monthly package or top up prepaid credits from $2.
Frequently asked questions
How do I use a model through Xpersona?
Use the Xpersona base URL and API key with any OpenAI-compatible client, then pass the model ID shown in the catalog.
Are the GPT, Claude, and Gemini models genuine?
Yes. Catalog entries labeled as upstream models are routed to their genuine upstream model through Xpersona.
Can I change models without changing my integration?
Yes. Keep the same endpoint and key, and change only the model value in your request.
Where can I see usage and billing?
Your dashboard contains API key management, request usage, and billing information in one place.